Senior Machine Learning Engineer, BenchSci

• You’re the perfect fit for this role if you are passionate about solving problems in NLP, have a great appreciation for science and want to transform how it is done
• Bachelor’s degree or higher in Computer Science, Mathematics, Machine Learning, Bioinformatics, or a related field
• Leadership: 2+ years of tech lead experience in a production ML environment
• Hands-on experience working with omics data and omics derived resources, such as genomic sequences, expression matrices, protein data, or biological networks
• Familiarity with omics and biomedical databases (e.g. gene/protein annotations, interaction networks, pathway databases, expression atlases)
• Experience with or strong interest in biological foundation models, such as sequence models, embedding models, or multi-modal models applied to molecular or cellular data
• Solid understanding of graph methods in a biological context, including knowledge graphs, molecular interaction networks, or pathway-level representations
• Experience applying NLP or LLM-based techniques to scientific text or integrating text-based evidence with structured biological data
• Strong experience with TensorFlow, PyTorch, and Omics processing libraries
• Comfort working across disciplines, collaborating closely with scientists, engineers, and product teams
• A team player who strives to see teammates succeed together
• A growth mindset, strong ownership mentality, and desire to work on scientifically meaningful problems
• You have a constant desire to grow and develop

Desirable

• We are looking for a Senior Machine Learning Engineer to join our growing R&D team
• Reporting into the Engineering Manager, R&D
• Build and deploy machine learning models over omics data (e.g. genomics, transcriptomics, proteomics, epigenomics, and multi-omics), capturing biological structure, variability, and experimental context
• Work with major omics and biomedical databases (e.g. gene, protein, pathway, interaction, and expression resources) to integrate heterogeneous biological signals into unified learning pipelines
• Develop and apply foundation models for biological data, including sequence-based, expression-based, and multi-modal models, adapting them to downstream scientific and product use cases
• Design ML systems that populate, enrich, and reason over a biological knowledge graph, connecting entities such as genes, proteins, pathways, phenotypes, diseases, and experimental evidence
• Apply graph-based methods tailored to biology, including graph embeddings, message passing, and network-aware learning, to model molecular interactions and biological systems
• Collaborate with BenchSci’s Science team to ensure models reflect biological constraints, experimental design, and domain nuance, not just statistical patterns
• Power downstream experiences by surfacing insights through semantic search, recommendation, and conversational AI / chat-based scientific assistants
• Improve scalability, robustness, and interpretability of models operating on large, sparse, noisy, and biased omics datasets
• Lead technical decision-making within the ML team, mentor other engineers, and help define best practices for applied ML in biomedical settings
• Own projects end-to-end, from data exploration and model prototyping to production deployment and monitoring
• Continuously improve the performance and scalability of ML models that are at the core of BenchSci’s products
• Regularly investigating what technologies will best enable BenchSci to effectively generate use cases
• Advocate for code and process improvements across yourteam, and help to define best practices based on personal industry experience and research
• Participate in sprint planning, estimation and reviews. Take ownership of deliverables, and work with teammates to ensure high-quality deliverables